Hi all,
Here's our (untimely) abstract. Any comments would be much appreciated.
Thanks,
Dennis & Jeremy
How Healthy Are We? A disadvantage to using ranked data for health state
valuation
Health state valuations (HSVs) constitute a fundamental building block for
measuring health system performance. To obtain HSVs, investigators often ask
respondents to value levels of disability using the time trade-off (TTO)
method. This procedure is costly, time-consuming, and difficult to
implement. Salomon (2003) proposes a model that estimates HSVs using only
ranked data, tests it with the 1993 British General Public Survey, and finds
the results nearly identical to a TTO-based model. We extend Salomon (2003)
by allowing HSVs to vary according to individual characteristics like age
and marital status, but find that some quantities of interest cannot be
estimated with the rank data. Our results show one limitation to using
ordinal data to measure cardinal quantities.
I agree with Dan. i'd save 'important' for cases when u are building some one up before u lower the boom. You're confirming their resilt so saying it is important is like being imodest about yout own work. (its always a fine line of course).
Also, use 'paper' not 'article' to describe your work. An article is a published paper.
And for everyone: pls don't forget to reread the 'publication, publication' paper about now. There are a lot of little things in there, all designed to make your papers better...
Gary
-----Original Message-----
From: Dan Hopkins <dhopkins(a)fas.harvard.edu>
Date: Monday, May 8, 2006 7:52 am
Subject: Re: [gov2001-l] It's not About Race at K - revised abstract
This is a very nice abstract. I might think about modifying your subtitle to give yourself a bit more independence from Fryer and Levitt--and to elaborate a bit on exactly how you contribute, since you have more data and new findings to offer.
Also, others might disagree with this, but I think that you should avoid characterizing others' contributions as being "important" or not.
Instead, I'd stick to the facts, and let the reader decide what is
important. In this case, I might say "Fryer and Levitt (2004), using data from a nationally representative sample of students in kindergarten and first grade, demonstrate that the disparity in academic achievement
between blacks and whites only begins after students arrive in school, after controlling for a small set of socioeconomic, family and health related characteristics." Your first two sentences have already convinced me that the topic is important...
Best,
Dan
On Mon, 8 May 2006, Elena Llaudet wrote:
> Good night everybody,
> Below is our revised abstract. Comments and criticisms are welcome.
Elena & Omar
> It's not About Race at K:
Confirming and Extending Fryer & Levitt's Understanding of the
Black-White Test Score Gap
by Elena Llaudet and Omar Wasow* *
> Although more than half a century has passed since the landmark /Brown
v. Board of Ed./ decision, black children continue to lag academically
behind their white peers. For decades, research comparing the test
scores of black and white students has consistently found a substantial
gap, even among four-year olds. Fryer and Levitt (2004), using data from
a nationally representative sample of students in kindergarten and first
grade, broke important ground when demonstrating that the disparity in
academic achievement between blacks and whites only begins after
students arrive in school, after controlling for a small set of
socioeconomic, family and health related characteristics. In this
article, we demonstrate the robustness of their results, expand their
analysis through fifth grade, and analyze the evolution of the gap in
the first six years of school with a model more appropriate for studying
cross-sectional and longitudinal data. We find that the divergence in
black and white test scores continues to grow after first grade,
although at a slower rate for math and at a similar rate for reading.
>
_______________________________________________
gov200
Good night everybody,
Below is our revised abstract. Comments and criticisms are welcome.
Elena & Omar
It's not About Race at K:
Confirming and Extending Fryer & Levitt's Understanding of the
Black-White Test Score Gap
by Elena Llaudet and Omar Wasow* *
Although more than half a century has passed since the landmark /Brown
v. Board of Ed./ decision, black children continue to lag academically
behind their white peers. For decades, research comparing the test
scores of black and white students has consistently found a substantial
gap, even among four-year olds. Fryer and Levitt (2004), using data from
a nationally representative sample of students in kindergarten and first
grade, broke important ground when demonstrating that the disparity in
academic achievement between blacks and whites only begins after
students arrive in school, after controlling for a small set of
socioeconomic, family and health related characteristics. In this
article, we demonstrate the robustness of their results, expand their
analysis through fifth grade, and analyze the evolution of the gap in
the first six years of school with a model more appropriate for studying
cross-sectional and longitudinal data. We find that the divergence in
black and white test scores continues to grow after first grade,
although at a slower rate for math and at a similar rate for reading.
Last minute comments?
In recent years, political methodologists, have produced innumerable automated
document ranking and classification systems. Many of these ignore word sequence
information, treating entire documents as mere collections of words. A subset of
these, including those based on the well-known Naive Bayes algorithm, assume
that word frequencies are unrelated and that word sequence information is
unimportant \cite{domingos96}. A recently developed algorithm known as
Wordscores makes an even wider set of assumptions \cite{wordscores2003}. In
this paper, we compare Wordscores to several more moderate document ranking,
classification, and summarization algorithms. Surprisingly, we find that
Wordscores shows remarkably improved performance at carrying out a small number
of carefully selected classifications on meticuously arranged collections of
political documents, demonstrate its performance at gauging the effects of news
headlines on S\&P 500 daily securities prices, and discuss its utility in other
applications.
Err...I mean Dan, not Dad....
Ian and Dad,
In Gary's How to Write a Paper article he mentions that we should all
use the American Journal of Political Science style for our
bibliography. If we are writing an article that will never, ever be
submitted to a political science journal, would it be okay to follow a
style more consistent with our field?
Karen
Ian and Dad,
In Gary's How to Write a Paper article he mentions that we should all
use the American Journal of Political Science style for our
bibliography. If we are writing an article that will never, ever be
submitted to a political science journal, would it be okay to follow a
style more consistent with our field?
Karen
Hi All,
So, I'll bet that subject line caught your attention--people care about
evaluations. So do we, the teaching staff. So... Please take a moment
*now*, while you are already online, to fill out an evaluation of 2001.
1) Go to: http://my.harvard.edu
2) Click on the "Courses" tab
3) Click on "Evaluate" next to Gov. 2001
Sorry to spam on this... but we promise to stop when the response rate
goes up! A classic collective action problem.
Best,
Dan
----
Ph.D. Student
Department of Government
Harvard University
Tutor, Currier House
dhopkins(a)fas.harvard.edu
http://www.danhopkins.org
"How Poverty Racializes Competition for City Council Seats"
Abstract
A growing body of literature has focused on the institutional and
electoral factors that lead to improved representation of minorities
on city councils. These studies, however, often employ OLS
regression, a methodology that can result in out-of-bounds predictions
for council membership. We employ a statistical model that produces
sensible results, in part by accounting for the zero-sum nature of
descriptive representation on city councils. Applying this model to a
recent study which argues that turnout increases representation for
minority groups (Hajnal and Trounstine 2005) we find little connection
between higher levels of voter turnout and greater descriptive
representation of minority groups. We find, instead, that poverty
provides an explanation, with higher numbers of black poor,
especially, leading to higher black and white representation at the
expense of Latinos. We conclude by arguing that the demographic
features that activate racial politics deserve greater attention in
studies of city council representation.
When trying to impute a binary variable using mice, I encounter this
error message in the first iteration,
> imp <- mice(Womendata, imputationMethod=imp.method)
iter imp variable
1 1 Approval.member Approval.Congress Trust.Index
Efficacy.Index Efficacy.Index2 CompetenceError in x[good, ] * w :
non-numeric argument to binary operator
My data table has the following dimension 15502 by 30. Competence is
a binary numeric variable with about 150 NA's. In my imp.method
vector, I have specified "logreg" as the method of imputation. Does
anyone have any suggestions as to what this error could mean.
Regards,
Sheldon
the title and abstract are ok as a summary of what I take it is your point, but the point is not so sharp. It looks like a list more than a clear substantive point. There may not be much u can do since what u write has to represent what u find of course, but sometimes u can rethink things in a different framework...
Gary
-----Original Message-----
From: Claire Allison Schwartz <cschwart(a)fas.harvard.edu>
Date: Friday, May 5, 2006 2:55 pm
Subject: [gov2001-l] Claire And Janet's Abstract
Here is our abstract. Thanks in advance for any comments.
Claire and Janet
-------------------------------
Why Do Civil Wars Recur?
Living Conditions, Attributes of the Prior War, and Autocracies Matter
Of civil wars that have ended since 1945, roughly one-third have
reignited. Walter (2004) argues that conditions conducive to rebel
recruitment - particularly poor living conditions and lack of access to political participation - are the critical precursors to renewed civil war. Using rare-events logit, model specification tests, and a hazard model on a respecified dataset, we demonstrate that Walter's findings are robust with three key exceptions: (1) living conditions matter, but less so than the characteristics of the previous war; (2) the magnitudes of her variables' impact are smaller than she estimated; and (3) when controlling for per capita GDP, civil war recurrence is less likely in autocratic states.
_______________________________________________
gov2001-l mailing list
gov2001-l(a)lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l